PBC4cip: A new contrast pattern-based classifier for class imbalance problems

Octavio Loyola-González, Miguel Angel Medina-Pérez, José Fco Martínez-Trinidad, Jesús Ariel Carrasco-Ochoa, Raúl Monroy, Milton García-Borroto

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

© 2016 Contrast pattern-based classifiers are an important family of both understandable and accurate classifiers. Nevertheless, these classifiers do not achieve good performance on class imbalance problems. In this paper, we introduce a new contrast pattern-based classifier for class imbalance problems. Our proposal for solving the class imbalance problem combines the support of the patterns with the class imbalance level at the classification stage of the classifier. From our experimental results, using highly imbalanced databases, we can conclude that our proposed classifier significantly outperforms the current contrast pattern-based classifiers designed for class imbalance problems. Additionally, we show that our classifier significantly outperforms other state-of-the-art classifiers not directly based on contrast patterns, which are also designed to deal with class imbalance problems.
Original languageAmerican English
Pages (from-to)100-109
Number of pages89
JournalKnowledge-Based Systems
DOIs
StatePublished - 1 Jan 2017
Externally publishedYes

Fingerprint

Classifiers
Classifier
Imbalance

Cite this

Loyola-González, O., Medina-Pérez, M. A., Martínez-Trinidad, J. F., Carrasco-Ochoa, J. A., Monroy, R., & García-Borroto, M. (2017). PBC4cip: A new contrast pattern-based classifier for class imbalance problems. Knowledge-Based Systems, 100-109. https://doi.org/10.1016/j.knosys.2016.10.018
Loyola-González, Octavio ; Medina-Pérez, Miguel Angel ; Martínez-Trinidad, José Fco ; Carrasco-Ochoa, Jesús Ariel ; Monroy, Raúl ; García-Borroto, Milton. / PBC4cip: A new contrast pattern-based classifier for class imbalance problems. In: Knowledge-Based Systems. 2017 ; pp. 100-109.
@article{30298807ea324dc49496389f2936e559,
title = "PBC4cip: A new contrast pattern-based classifier for class imbalance problems",
abstract = "{\circledC} 2016 Contrast pattern-based classifiers are an important family of both understandable and accurate classifiers. Nevertheless, these classifiers do not achieve good performance on class imbalance problems. In this paper, we introduce a new contrast pattern-based classifier for class imbalance problems. Our proposal for solving the class imbalance problem combines the support of the patterns with the class imbalance level at the classification stage of the classifier. From our experimental results, using highly imbalanced databases, we can conclude that our proposed classifier significantly outperforms the current contrast pattern-based classifiers designed for class imbalance problems. Additionally, we show that our classifier significantly outperforms other state-of-the-art classifiers not directly based on contrast patterns, which are also designed to deal with class imbalance problems.",
author = "Octavio Loyola-Gonz{\'a}lez and Medina-P{\'e}rez, {Miguel Angel} and Mart{\'i}nez-Trinidad, {Jos{\'e} Fco} and Carrasco-Ochoa, {Jes{\'u}s Ariel} and Ra{\'u}l Monroy and Milton Garc{\'i}a-Borroto",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.knosys.2016.10.018",
language = "American English",
pages = "100--109",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

Loyola-González, O, Medina-Pérez, MA, Martínez-Trinidad, JF, Carrasco-Ochoa, JA, Monroy, R & García-Borroto, M 2017, 'PBC4cip: A new contrast pattern-based classifier for class imbalance problems', Knowledge-Based Systems, pp. 100-109. https://doi.org/10.1016/j.knosys.2016.10.018

PBC4cip: A new contrast pattern-based classifier for class imbalance problems. / Loyola-González, Octavio; Medina-Pérez, Miguel Angel; Martínez-Trinidad, José Fco; Carrasco-Ochoa, Jesús Ariel; Monroy, Raúl; García-Borroto, Milton.

In: Knowledge-Based Systems, 01.01.2017, p. 100-109.

Research output: Contribution to journalArticle

TY - JOUR

T1 - PBC4cip: A new contrast pattern-based classifier for class imbalance problems

AU - Loyola-González, Octavio

AU - Medina-Pérez, Miguel Angel

AU - Martínez-Trinidad, José Fco

AU - Carrasco-Ochoa, Jesús Ariel

AU - Monroy, Raúl

AU - García-Borroto, Milton

PY - 2017/1/1

Y1 - 2017/1/1

N2 - © 2016 Contrast pattern-based classifiers are an important family of both understandable and accurate classifiers. Nevertheless, these classifiers do not achieve good performance on class imbalance problems. In this paper, we introduce a new contrast pattern-based classifier for class imbalance problems. Our proposal for solving the class imbalance problem combines the support of the patterns with the class imbalance level at the classification stage of the classifier. From our experimental results, using highly imbalanced databases, we can conclude that our proposed classifier significantly outperforms the current contrast pattern-based classifiers designed for class imbalance problems. Additionally, we show that our classifier significantly outperforms other state-of-the-art classifiers not directly based on contrast patterns, which are also designed to deal with class imbalance problems.

AB - © 2016 Contrast pattern-based classifiers are an important family of both understandable and accurate classifiers. Nevertheless, these classifiers do not achieve good performance on class imbalance problems. In this paper, we introduce a new contrast pattern-based classifier for class imbalance problems. Our proposal for solving the class imbalance problem combines the support of the patterns with the class imbalance level at the classification stage of the classifier. From our experimental results, using highly imbalanced databases, we can conclude that our proposed classifier significantly outperforms the current contrast pattern-based classifiers designed for class imbalance problems. Additionally, we show that our classifier significantly outperforms other state-of-the-art classifiers not directly based on contrast patterns, which are also designed to deal with class imbalance problems.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84995975051&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84995975051&origin=inward

U2 - 10.1016/j.knosys.2016.10.018

DO - 10.1016/j.knosys.2016.10.018

M3 - Article

SP - 100

EP - 109

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -